Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words associated with chemical elements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'aph', indicating a focus on specific chemical or biological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Runner
    -0.71
     ranks
    -0.69
     top
    -0.64
    LINE
    -0.63
     Git
    -0.60
     standard
    -0.60
     Tart
    -0.60
     pay
    -0.60
     return
    -0.58
     slack
    -0.58
    POSITIVE LOGITS
    aph
    4.66
    APH
    1.88
    oph
    1.32
    eph
    1.24
    iph
    1.23
    ph
    1.14
    het
    1.11
    ap
    1.10
    ophobia
    1.08
    alf
    1.06
    Act Density 0.010%

    No Known Activations